p-based loss function

[T-nfd]

Dear @zengh5

I read your great paper, "A comparison study of CNN denoisers on PRNU extraction."
I have a model that I've defined as criterion = nn.CrossEntropyLoss().to(device).
So in the training part I have loss = criterion(outputs, labels)
I want to use your p-based loss function, but I don't know how?
Could you please help me with that?

[zengh5]

Dear T-nfd:
Thanks for your interesting. Can you explain your issue more clearly and send it to my email [email protected]

[JhxxxQ]

Hello @T-nfd , I doing some researches about sci too, could you leave your email for communication?
Thank you!